framework
active
framework:interpretability-as-natural-scienceInterpretability as Natural Science
Proposed paradigm for evaluating interpretability work through empirical falsifiability rather than benchmarks or user studies
Neighborhood — ranked by edge-count
Papers (1)
paper
- Zoom In: An Introduction to Circuitsintroduces
Concepts (1)
concept
- The field aimed at understanding what neural networks have learned; characterized as pre-paradigmatic in this paper
Claims (1)
claim
- Argument that circuits methodology meets natural-science standards of falsifiability
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
- Socio-philosophical open question.
- Method using large language models (Claude) to generate and test explanations of features at scale
- Explaining activations without understanding mechanism.
- Frames model interpretability like biology, features as cells, tools as microscopes.
- Structure SAEs miss.
- Second approach: propose concepts and find components corresponding to them.
- Cases where subspace interventions change model behaviour through parallel pathways rather than the target feature